Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    technical terms related to mathematical or physical concepts, particularly in symmetry and periodic systems

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Fus
    -0.52
     generalised
    -0.51
    ########.
    -0.50
     Ting
    -0.50
    IsContent
    -0.50
    jupiter
    -0.49
     weaning
    -0.47
    shund
    -0.46
     pokoj
    -0.45
     SETTLE
    -0.45
    POSITIVE LOGITS
     cycle
    0.85
     cycles
    0.75
     loop
    0.74
     revient
    0.71
     loops
    0.71
     recirc
    0.71
     Cycle
    0.68
     Cycles
    0.68
     return
    0.64
     Wieder
    0.64
    Act Density 0.639%

    No Known Activations